gpudiff the public record of change in GPU cloud pricing

qwen2.5-vl-72b-instruct API price — 3 gateways compared

from $0.80 per million input tokens · same price on every gateway · updated hourly

Fees beyond the token price

• OpenRouter: No markup on token prices (provider pass-through), but credit purchases cost 5.5% via card ($0.80 minimum) or 5% via crypto; BYOK usage above the monthly allowance is charged 5%. source

Changelog for qwen2.5-vl-72b-instruct

• 2026-08-17 openrouter listed qwen-qwen2.5-vl-72b-instruct-input at 0.8 usd_per_mtok
• 2026-08-16 openrouter raised qwen-qwen2.5-vl-72b-instruct-output 33.3%: 0.75 → 1.0 usd_per_mtok
• 2026-08-16 openrouter delisted qwen-qwen2.5-vl-72b-instruct-input

qwen2.5-vl-72b-instruct pricing FAQ

How much does qwen2.5-vl-72b-instruct cost per million tokens?

The cheapest tracked gateway charges $0.80 per million input tokens and $0.80 per million output tokens (Glama). Prices refresh hourly.

Which gateway is cheapest for qwen2.5-vl-72b-instruct?

Glama for input tokens and Novita for output tokens, among the 3 gateways we track.

Do qwen2.5-vl-72b-instruct prices differ between gateways?

No — every tracked gateway currently charges the same per-token price, so the difference between them is fees and routing, not token cost.

← All LLM prices · API